Last active
July 3, 2019 12:34
-
-
Save tsundokul/8dcd93b63a6f2bee57a23ee2b2baf248 to your computer and use it in GitHub Desktop.
Script that downloads the most popular WordPress plugins
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import requests | |
from lxml import html | |
# Make sure you have a directory named wp_plugins/ in the cwd | |
def get_links(url): | |
page = requests.get(url) | |
webpage = html.fromstring(page.content) | |
links = webpage.xpath('//div/main/article//div[2]/header/h2/a/@href') | |
for i, link in enumerate(links): | |
print("{}. {}".format(i, link)) | |
download_link(link, str(i)) | |
def download_link(link, i): | |
page = requests.get(link) | |
webpage = html.fromstring(page.content) | |
dl_link = webpage.xpath("//a[text()='Download']/@href")[0] | |
name = "wp_plugins/" + dl_link.split("/")[-1] | |
headers = { | |
'User-Agent': "Mozilla/5.0 (X11; Linux x86_64; rv:63.0) Gecko/20100101 Firefox/63.0", | |
'Referer': link, | |
'Accept-Language': 'en-US,en;q=0.5', | |
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' | |
} | |
r = requests.get(dl_link, stream=True, headers=headers) | |
if r.status_code == 200: | |
with open(name, 'wb') as f: | |
for chunk in r: | |
f.write(chunk) | |
else: | |
print(r.status_code) | |
for i in range(1, 100): | |
print("========== PAGE {}".format(i)) | |
get_links('https://wordpress.org/plugins/browse/popular/page/' + str(i)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment